Machine Learning Enables Selection of Epistatic Enzyme Mutants for Stability Against Unfolding and Detrimental Aggregation.

Machine learning (ML) has pervaded most areas of protein engineering, including stability and stereoselectivity. Using limonene epoxide hydrolase as the model enzyme and innov'SAR as the ML platform, comprising a digital signal process, we achieved high protein robustness that can resist unfolding with concomitant detrimental aggregation. Fourier transform (FT) allows us to take into account the order of the protein sequence and the nonlinear interactions between positions, and thus to grasp epistatic phenomena. The innov'SAR approach is interpolative, extrapolative and makes outside-the-box, predictions not found in other state-of-the-art ML or deep learning approaches. Equally significant is the finding that our approach to ML in the present context, flanked by advanced molecular dynamics simulations, uncovers the connection between epistatic mutational interactions and protein robustness.

One-shot optimization of multiple enzyme parameters: Tailoring glucose oxidase for pH and electron mediators.

Enzymes are biological catalysts with many industrial applications, but natural enzymes are usually unsuitable for industrial processes because they are not optimized for the process conditions. The properties of enzymes can be improved by directed evolution, which involves multiple rounds of mutagenesis and screening. By using mathematical models to predict the structure-activity relationship of an enzyme, and by defining the optimal combination of mutations in silico, we can significantly reduce the number of bench experiments needed, and hence the time and investment required to develop an optimized product. Here, we applied our innovative sequence-activity relationship methodology (innov'SAR) to improve glucose oxidase activity in the presence of different mediators across a range of pH values. Using this machine learning approach, a predictive model was developed and the optimal combination of mutations was determined, leading to a glucose oxidase mutant (P1) with greater specificity for the mediators ferrocene-methanol (12-fold) and nitrosoaniline (8-fold), compared to the wild-type enzyme, and better performance in three pH-adjusted buffers. The kcat /KM ratio of P1 increased by up to 121 folds compared to the wild type enzyme at pH 5.5 in the presence of ferrocene methanol.

New insights into GluT1 mechanics during glucose transfer.

Glucose plays a crucial role in the mammalian cell metabolism. In the erythrocytes and endothelial cells of the blood-brain barrier, glucose uptake is mediated by the glucose transporter type 1 (GluT1). GluT1 deficiency or mutations cause severe physiological disorders. GluT1 is also an important target in cancer therapy as it is overexpressed in tumor cells. Previous studies have suggested that GluT1 mediates solute transfer through a cycle of conformational changes. However, the corresponding 3D structures adopted by the transporter during the transfer process remain elusive. In the present work, we first elucidate the whole conformational landscape of GluT1 in the absence of glucose, using long molecular dynamics simulations and show that the transitions can be accomplished through thermal fluctuations. Importantly, we highlight a strong coupling between intracellular and extracellular domains of the protein that contributes to the transmembrane helices reorientation during the transition. The conformations adopted during the simulations differ from the known 3D bacterial homologs structures resolved in similar states. In holo state simulations, we find that glucose transits along the pathway through significant rotational motions, while maintaining hydrogen bonds with the protein. These persistent motions affect side chains orientation, which impacts protein mechanics and allows glucose progression.

A machine learning approach for reliable prediction of amino acid interactions and its application in the directed evolution of enantioselective enzymes.

Directed evolution is an important research activity in synthetic biology and biotechnology. Numerous reports describe the application of tedious mutation/screening cycles for the improvement of proteins. Recently, knowledge-based approaches have facilitated the prediction of protein properties and the identification of improved mutants. However, epistatic phenomena constitute an obstacle which can impair the predictions in protein engineering. We present an innovative sequence-activity relationship (innov'SAR) methodology based on digital signal processing combining wet-lab experimentation and computational protein design. In our machine learning approach, a predictive model is developed to find the resulting property of the protein when the n single point mutations are permuted (2n combinations). The originality of our approach is that only sequence information and the fitness of mutants measured in the wet-lab are needed to build models. We illustrate the application of the approach in the case of improving the enantioselectivity of an epoxide hydrolase from Aspergillus niger. n = 9 single point mutants of the enzyme were experimentally assessed for their enantioselectivity and used as a learning dataset to build a model. Based on combinations of the 9 single point mutations (29), the enantioselectivity of these 512 variants were predicted, and candidates were experimentally checked: better mutants with higher enantioselectivity were indeed found.

Application of fourier transform and proteochemometrics principles to protein engineering.

BACKGROUND: Connecting the dots between the protein sequence and its function is of fundamental interest for protein engineers. In-silico methods are useful in this quest especially when structural information is not available. In this study we propose a mutant library screening tool called iSAR (innovative Sequence Activity Relationship) that relies on the physicochemical properties of the amino acids, digital signal processing and partial least squares regression to uncover these sequence-function correlations. RESULTS: We show that the digitalized representation of the protein sequence in the form of a Fourier spectrum can be used as an efficient descriptor to model the sequence-activity relationship of proteins. The iSAR methodology that we have developed identifies high fitness mutants from mutant libraries relying on physicochemical properties of the amino acids, digital signal processing and regression techniques. iSAR correlates variations caused by mutations in spectra with biological activity/fitness. It takes into account the impact of mutations on the whole spectrum and does not focus on local fitness alone. The utility of the method is illustrated on 4 datasets: cytochrome P450 for thermostability, TNF-alpha for binding affinity, GLP-2 for potency and enterotoxins for thermostability. The choice of the datasets has been made such as to illustrate the ability of the method to perform when limited training data is available and also when novel mutations appear in the test set, that have not been featured in the training set. CONCLUSION: The combination of Fast Fourier Transform and Partial Least Squares regression is efficient in capturing the effects of mutations on the function of the protein. iSAR is a fast algorithm which can be implemented with limited computational resources and can make effective predictions even if the training set is limited in size.

Comparative genomics of odorant binding proteins in Anopheles gambiae, Aedes aegypti, and Culex quinquefasciatus.

About 1 million people in the world die each year from diseases spread by mosquitoes, and understanding the mechanism of host identification by the mosquitoes through olfaction is at stake. The role of odorant binding proteins (OBPs) in the primary molecular events of olfaction in mosquitoes is becoming an important focus of biological research in this area. Here, we present a comprehensive comparative genomics study of OBPs in the three disease-transmitting mosquito species Anopheles gambiae, Aedes aegypti, and Culex quinquefasciatus starting with the identification of 110 new OBPs in these three genomes. We have characterized their genomic distribution and orthologous and phylogenetic relationships. The diversity and expansion observed with respect to the Aedes and Culex genomes suggests that the OBP gene family acquired functional diversity concurrently with functional constraints posed on these two species. Sequences with unique features have been characterized such as the "two-domain OBPs" (previously known as Atypical OBPs) and "MinusC OBPs" in mosquito genomes. The extensive comparative genomics featured in this work hence provides useful primary insights into the role of OBPs in the molecular adaptations of mosquito olfactory system and could provide more clues for the identification of potential targets for insect repellants and attractants.